cturan/llama.cpp

작성자	SHA1 메시지	날짜
cturan	54ed0123a6 Add minimax model support	2 달 전
Johannes Gäßler	945501f5ea llama: fix leaked buffers for mmap + split files (#16765)	2 달 전
Aman Gupta	75cbdd3fce test-backend-ops: print failed tests at the end (#16785)	2 달 전
tamarPal	2b9bd9bf4e sycl: add ROLL operation support (#16665)	2 달 전
shani-f	59fc1ec8e8 sycl: add REPEAT_BACK operation support (#16734)	2 달 전
Aman Gupta	75d33b9302 CUDA: support for weight clamp in top-k norm (#16702)	2 달 전
Acly	3470a5c891 ggml-alloc : make gallocr prefer chunks that allow memory reuse (#16788)	2 달 전
Sigbjørn Skjæret	bd562fe4f7 cuda : use fast copy when src and dst are of different type and contiguous (#16789)	2 달 전
leejet	bbac6a26b2 ggml: fix cuda kernel launch configuration for k_compute_batched_ptrs to support large batch (#16744)	2 달 전
Sigbjørn Skjæret	73a48c9790 convert : enable expert group selection for all models with it (#16691)	2 달 전
Sigbjørn Skjæret	f696428ce8 graph : add clamping to ffn_moe_weights_sum to avoid div-by-zero (#16655)	2 달 전
Sigbjørn Skjæret	7cce4f8158 model : set res->t_embd in SmallThinker models (#16782)	2 달 전
amirai21	8d8862829c docs : add Jamba to Text-only models list (#16778)	2 달 전
Aman Gupta	f77c13b91f CUDA: General GEMV fusion (#16715)	2 달 전
Gilad S.	3cfa9c3f12 vulkan: deduplicate Microsoft Direct3D12 devices (#16689)	2 달 전
Galunid	5d195f17bc convert : handle mmproj filename/path properly (#16760)	2 달 전
Shunta Saito	226f295f4d model : set res->t_embd in PLaMo2 models (#16766)	2 달 전
Giuseppe Scrivano	f90b4a8efe vulkan: delete dead code (#16732)	2 달 전
Jeff Bolz	8423d01931 vulkan: Optimize SSM_SCAN (#16645)	2 달 전
compilade	5cca2542ac convert : avoid dequantizing mxfp4 for GPT-OSS (#16756)	2 달 전
leejet	55945d2ef5 ggml: fix CUDA grid launch condition for large block_nums.y in binbcast (#16742)	2 달 전
Aman Gupta	0bcb40b48c CUDA: use CUB for arbitary size argsort (#16754)	2 달 전
Florian Badie	69e9ff0103 webui: support q URL parameter (#16728)	2 달 전
Daniel Bevenius	5a91109a5d model-conversion : add trust_remote_code for orig model run [no ci] (#16751)	2 달 전
compilade	f8f071fadd convert : handle pre-quantized models (#14810)	2 달 전
Johannes Gäßler	0bf47a1dbb server: add memory breakdown print (#16740)	2 달 전
Julien Denize	dd62dcfab9 convert : Make mistral-common dependency optional (#16738)	2 달 전
Xuan-Son Nguyen	d0660f237a mtmd-cli : allow using --jinja (#16718)	2 달 전
Prajwal B Mehendarkar	fe6a9882ac Manually link -lbsd to resolve flock symbol on AIX (#16610)	2 달 전
Aman Gupta	061f0eff02 ggml-cuda: use passed ops instead of hardcoded ops (#16712)	2 달 전

최신 이전

커밋 기록 찾기

커밋 기록